Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add iwe-org/dev-workspace --skill plangit clone --depth 1 https://github.com/iwe-org/dev-workspaceWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/iwe-org/dev-workspace/plan)<a href="https://agentmods.dev/skills/iwe-org/dev-workspace/plan"><img src="https://agentmods.dev/badge/skills/iwe-org/dev-workspace/plan/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/iwe-org/dev-workspace/plan"><img src="https://agentmods.dev/badge/skills/iwe-org/dev-workspace/plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00068 | $0.00743 |
| Opus 5.5 | $0.00027 | $0.00297 |
| Sonnet 5.5 | $0.00014 | $0.00149 |
| Haiku 4.5 | $0.00007 | $0.00074 |
Grade A, and why
plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan a piece of work
A plan is a promise a future session can execute without re-deriving context. Discovery happens in the codebase before a word is written; every anchor is verified, every touched spec is named.
Steps
-
Consult. Read
data/product.md— especially## Constraintsand## Authoring rules, which bind what you write. Check for related work:iwe find --fuzzy <topic> -f keys, the relevantdata/spec/anddata/features/docs, and whether an active plan already covers this (iwe find --included-by data/plans -f keys). -
Discover. Read the code the plan will touch. Collect the entry points, the functions to modify, and their current line numbers — these become
## Key references, and they must come from the current checkout, not memory. -
Create.
iwe new --key data/plans/<YYYYMMDD>-<slug>(today's date, kebab slug), then write:--- created: <today> ---Body sections, in order (omit a section only when it's genuinely empty):
## Context— why now, linking the feature/bug/backlog doc that motivates it## Approach— the shape of the solution and the alternative you rejected, in a few sentences## Implementation Steps—### Task N: <name>blocks, each with**Files:** Create:/Modify: ...and- [ ]checkboxes## Spec changes— everydata/spec/doc this work will create or change; name not-yet-existing specs in back-ticks (never dangling links)## Depends on— inline links to plans that must ship first (omit if none)## Verification— how a session proves the work is done: commands, tests, manual checks## Out of scope— what this plan deliberately does not do## Key references—path:line — symbollist under a lineVerified anchor points (line numbers as of <today>):
-
File it. Add an inclusion link under
## Activeindata/plans.md. If the plan implements a proposed feature, set the feature doc tostage: accepted. If it grew from a backlog task, mark the task done and move its link. -
Validate.
iwe normalize, theniwe schema validate— must pass.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 64 lines · 68 tokens per session scan A b066bcbfaa80
plan is a skill published in the GitHub repository iwe-org/dev-workspace (10 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 743 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
agent-state-bar
A design guide for an agent status bar: a short, automatically updated summary of progress, remaining tasks, tool counts, errors, and system state placed near the latest model input.
context-engineering
A guide to organizing the instructions and information an AI agent receives at each step. It covers system prompts, tool descriptions, conversation history, on-demand skills, and protections against unsafe outside content.
kv-cache-design
A guide to arranging an AI agent's conversation so previously processed text can be reused. A KV cache stores intermediate results for earlier tokens, while a prompt cache reuses a stable beginning across requests.
loop-engineering
A guide to building reliable loops for AI agents that plan, act, check their work, and continue until a task is truly complete. It includes independent verification and a proposer-reviewer pattern in which one agent's work is checked using outside evidence.
multi-agent-design
A guide to deciding when several AI agents should work together and how they should share tasks, context, and files. It compares peer, manager-led, and decentralised arrangements and explains common coordination failures.
reward-design
A guide to defining the scores that an AI agent receives during trial-and-error training. It covers checks based on rules, human preferences, or another model, and distinguishes rewarding the final result from rewarding the steps taken.